Duplicated from zhengr/inference
24de499 87dd288 24de499
1
2
3
4
5
6
7
8
9
10
#!/bin/bash # Starting server echo "Starting server" echo "Running" $MODEL_URL ./llama-server --model-url $MODEL_URL --reranking --port 7860 --host 0.0.0.0 # Keep the script running to prevent the container from exiting wait
